A coding agent plugin that acts as a safety net, catching destructive git and filesystem commands before they execute.
-
Updated
Mar 21, 2026 - TypeScript
#
destructive-commands
Here are 5 public repositories matching this topic...
Claude Code plugin: scope-aware protection — allows destructive ops (rm, mv, chmod) within project, blocks them outside. Built for dangerouslySkipPermissions mode.
developer-tools safety claude-code claude-code-plugin destructive-commands dangerously-skip-permissions project-boundary cli-safety
-
Updated
Mar 10, 2026 - Shell
Runtime guardrails for Claude Code. Classifies every sensitive action by risk tier, enforces proportional controls (notify / approve / halt), blocks dangerous operations with hard constraints, and logs a full audit trail. Zero dependencies. One install.
-
Updated
Mar 20, 2026 - Python
🛡️ Enhance code safety with Claude Code Safety Net, a tool designed to identify and mitigate risks in your codebase effectively.
agent machine-learning ai tasks autonomous-agents npx tasks-list windsurf jules ai-tools agentic-framework agentic-rag agentic-ai cursorai cursor-ai model-context-protocol mcp-server windsurf-ai claude-code destructive-commands
-
Updated
Mar 22, 2026 - TypeScript
Claude Code plugin that prevents destructive commands, blocks credential exposure, and redirects dangerous operations to safer alternatives
-
Updated
Mar 13, 2026 - Python
Improve this page
Add a description, image, and links to the destructive-commands topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the destructive-commands topic, visit your repo's landing page and select "manage topics."